Using an adaptive VAR Model for motion prediction in 3D hand tracking

A robust VAR-based (vector autoregressive) model is introduced for motion prediction in 3D hand tracking. This dynamic VAR motion model is learned in an online manner. The kinematic structure of the hand is accounted for in the form of constraints when solving for the parameters of the VAR model. Also integrated into the motion prediction model are adaptive weights that are optimised according to the reliability of past predictions. Experiments on synthetic and real video sequences show a substantial improvement in tracking performance when the robust VAR motion model is used. In fact, utilising the robust VAR model allows the tracker to handle fast out-of-plane hand movement with severe self-occlusion.

[1]  Neil A. Thacker,et al.  Real-time Body Tracking Using a Gaussian Process Latent Variable Model , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[2]  Luc Van Gool,et al.  Fast stochastic optimization for articulated structure tracking , 2007, Image Vis. Comput..

[3]  Nicol N. Schraudolph,et al.  3D Hand Tracking in a Stochastic Approximation Setting , 2007, Workshop on Human Motion.

[4]  Björn Stenger,et al.  Model-based hand tracking using a hierarchical Bayesian filter , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Helmut Ltkepohl,et al.  New Introduction to Multiple Time Series Analysis , 2007 .

[6]  Anthony C. Atkinson,et al.  Robust Diagnostic Regression Analysis , 2000 .

[7]  Michael J. Black,et al.  Implicit Probabilistic Models of Human Motion for Synthesis and Tracking , 2002, ECCV.

[8]  Nicol N. Schraudolph,et al.  Local Gain Adaptation in Stochastic Gradient Descent , 1999 .

[9]  Ankur Agarwal,et al.  Tracking Articulated Motion Using a Mixture of Autoregressive Models , 2004, ECCV.

[10]  James M. Rehg,et al.  Statistical Color Models with Application to Skin Detection , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[11]  Eugene Fiume,et al.  Helping hand: an anatomically accurate inverse dynamics solution for unconstrained hand motion , 2005, SCA '05.

[12]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[13]  Yen-Wei Chen,et al.  Articulated hand tracking by PCA-ICA approach , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[14]  Thomas S. Huang,et al.  Tracking articulated hand motion with eigen dynamics analysis , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  Lutz Kilian,et al.  NEW INTRODUCTION TO MULTIPLE TIME SERIES ANALYSIS, by Helmut Lütkepohl, Springer, 2005 , 2006, Econometric Theory.